Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1452 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0775. Min Act: -0.0005

Data Index: 593361 (C4 (Web Text))

Max Activating Token Index: 460

Text #1

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0717. Min Act: -0.0005

Data Index: 1298696 (C4 (Web Text))

Max Activating Token Index: 945

Text #2

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0687. Min Act: -0.0005

Data Index: 909364 (C4 (Web Text))

Max Activating Token Index: 347

Text #3

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0707. Min Act: -0.0005

Data Index: 705238 (C4 (Web Text))

Max Activating Token Index: 809

Text #4

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0658. Min Act: -0.0005

Data Index: 735176 (C4 (Web Text))

Max Activating Token Index: 29

Text #5

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0648. Min Act: -0.0005

Data Index: 989805 (C4 (Web Text))

Max Activating Token Index: 31

Text #6

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0646. Min Act: -0.0005

Data Index: 808045 (C4 (Web Text))

Max Activating Token Index: 737

Text #7

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0613. Min Act: -0.0005

Data Index: 310686 (C4 (Web Text))

Max Activating Token Index: 648

Text #8

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0613. Min Act: -0.0005

Data Index: 716624 (C4 (Web Text))

Max Activating Token Index: 62

Text #9

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0612. Min Act: -0.0005

Data Index: 1352824 (C4 (Web Text))

Max Activating Token Index: 697

Text #10

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0670. Min Act: -0.0005

Data Index: 1176943 (C4 (Web Text))

Max Activating Token Index: 331

Text #11

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0608. Min Act: -0.0005

Data Index: 1111160 (C4 (Web Text))

Max Activating Token Index: 647

Text #12

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0613. Min Act: -0.0005

Data Index: 1045577 (C4 (Web Text))

Max Activating Token Index: 656

Text #13

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0591. Min Act: -0.0005

Data Index: 1183152 (C4 (Web Text))

Max Activating Token Index: 702

Text #14

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0614. Min Act: -0.0005

Data Index: 546600 (C4 (Web Text))

Max Activating Token Index: 1010

Text #15

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0589. Min Act: -0.0005

Data Index: 82541 (C4 (Web Text))

Max Activating Token Index: 870

Text #16

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0581. Min Act: -0.0005

Data Index: 564845 (C4 (Web Text))

Max Activating Token Index: 721

Text #17

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0579. Min Act: -0.0005

Data Index: 1372527 (Python Code)

Max Activating Token Index: 238

Text #18

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0578. Min Act: -0.0005

Data Index: 281440 (C4 (Web Text))

Max Activating Token Index: 16

Text #19

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0584. Min Act: -0.0005

Data Index: 723653 (C4 (Web Text))

Max Activating Token Index: 27